© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53937
    Prev
    Next
    INDEX
    Explanations

    department of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رة
    -0.09
    åĪ¸
    -0.08
    GRAM
    -0.08
    .WinForms
    -0.08
    让æ¶Īè´¹èĢħ
    -0.08
     Amen
    -0.08
     onCreateView
    -0.08
    ç´Ĭ
    -0.08
    пÑĥÑĤ
    -0.08
    ç»ıæµİåŃ¦å®¶
    -0.08
    POSITIVE LOGITS
    obb
    0.10
    纸ä¸Ĭ
    0.09
    表æĥħ
    0.08
    就说
    0.08
    åıĪ好åıĪ
    0.08
    eldorf
    0.08
    lon
    0.08
    æĴ¼
    0.08
    weeney
    0.08
    åħ´è¶£
    0.08
    Activations Density 0.046%

    No Known Activations